import os import gradio as gr import requests import inspect import pandas as pd import json import re from typing import Dict, Any from dotenv import load_dotenv from openai import OpenAI from tenacity import retry, stop_after_attempt, wait_exponential # Load environment variables load_dotenv() # (Keep Constants as is) # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" OPENAI_MODEL = ( "gpt-4-turbo-preview" # Using OpenAI's latest model for better performance ) # --- Basic Agent Definition --- # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------ class BasicAgent: def __init__(self): """Initialize the agent with OpenAI client and setup.""" print("BasicAgent initializing...") self.client = OpenAI(api_key=os.getenv("OPENAI_API_KEY")) self.question_history: Dict[str, Any] = {} # Store question context print("BasicAgent initialized successfully.") def _format_answer(self, raw_answer: str) -> str: """Format the answer to improve exact matching success.""" # Remove any explanations or reasoning if "Answer:" in raw_answer: answer = raw_answer.split("Answer:")[-1].strip() elif "Final answer:" in raw_answer: answer = raw_answer.split("Final answer:")[-1].strip() else: answer = raw_answer.strip() # Clean up formatting answer = re.sub( r"\s+", " ", answer ) # Replace multiple spaces with single space answer = answer.strip("\"'") # Remove quotes answer = answer.strip(".") # Remove trailing periods return answer.strip() @retry( stop=stop_after_attempt(3), wait=wait_exponential(multiplier=1, min=4, max=10) ) def _get_completion(self, messages: list) -> str: """Get completion from OpenAI with retry logic.""" try: response = self.client.chat.completions.create( model=OPENAI_MODEL, messages=messages, temperature=0.1, # Lower temperature for more consistent outputs max_tokens=1000, ) return response.choices[0].message.content.strip() except Exception as e: print(f"Error in OpenAI API call: {e}") raise def _analyze_question(self, question: str) -> dict: """Analyze the question to determine its type and required approach.""" system_msg = """You are an expert at analyzing questions. For the given question: 1. Identify the question type (e.g., factual, calculation, reasoning) 2. Identify key entities and concepts 3. Determine if external knowledge is needed 4. Suggest the best approach to answer it Provide your analysis in JSON format.""" messages = [ {"role": "system", "content": system_msg}, {"role": "user", "content": f"Analyze this question: {question}"}, ] try: analysis = self._get_completion(messages) return json.loads(analysis) except: return {"type": "unknown", "approach": "direct"} def _get_answer(self, question: str, analysis: dict) -> str: """Get the answer based on question analysis.""" system_prompt = f"""You are an AI assistant specialized in answering GAIA benchmark questions. Your task is to provide EXACT, PRECISE answers that can be matched against a ground truth. Guidelines: 1. Provide ONLY the final answer, no explanations 2. Be extremely precise and consistent in formatting 3. For numerical answers, use digits (e.g., "42" not "forty-two") 4. For lists, use comma-separated values without spaces after commas 5. For yes/no questions, answer only with "Yes" or "No" 6. Remove any punctuation from the end of your answer 7. Keep your answer as concise as possible while being complete Question type: {analysis.get('type', 'unknown')} Approach: {analysis.get('approach', 'direct')} Remember: Your answer will be compared EXACTLY with the ground truth. Format matters!""" messages = [ {"role": "system", "content": system_prompt}, {"role": "user", "content": question}, ] raw_answer = self._get_completion(messages) return self._format_answer(raw_answer) def __call__(self, question: str) -> str: """Process the question and return an answer.""" print(f"Agent received question (first 50 chars): {question[:50]}...") try: # Analyze the question analysis = self._analyze_question(question) print(f"Question analysis: {json.dumps(analysis, indent=2)}") # Get and format the answer answer = self._get_answer(question, analysis) print(f"Generated answer: {answer}") # Store question context self.question_history[question] = {"analysis": analysis, "answer": answer} return answer except Exception as e: print(f"Error processing question: {e}") return f"Error: {str(e)}" def run_and_submit_all(profile: gr.OAuthProfile | None): """ Fetches all questions, runs the BasicAgent on them, submits all answers, and displays the results. """ # --- Determine HF Space Runtime URL and Repo URL --- space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code if profile: username = f"{profile.username}" print(f"User logged in: {username}") else: print("User not logged in.") return "Please Login to Hugging Face with the button.", None api_url = DEFAULT_API_URL questions_url = f"{api_url}/questions" submit_url = f"{api_url}/submit" # 1. Instantiate Agent ( modify this part to create your agent) try: agent = BasicAgent() except Exception as e: print(f"Error instantiating agent: {e}") return f"Error initializing agent: {e}", None # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public) agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" print(agent_code) # 2. Fetch Questions print(f"Fetching questions from: {questions_url}") try: response = requests.get(questions_url, timeout=15) response.raise_for_status() questions_data = response.json() if not questions_data: print("Fetched questions list is empty.") return "Fetched questions list is empty or invalid format.", None print(f"Fetched {len(questions_data)} questions.") except requests.exceptions.RequestException as e: print(f"Error fetching questions: {e}") return f"Error fetching questions: {e}", None except requests.exceptions.JSONDecodeError as e: print(f"Error decoding JSON response from questions endpoint: {e}") print(f"Response text: {response.text[:500]}") return f"Error decoding server response for questions: {e}", None except Exception as e: print(f"An unexpected error occurred fetching questions: {e}") return f"An unexpected error occurred fetching questions: {e}", None # 3. Run your Agent results_log = [] answers_payload = [] print(f"Running agent on {len(questions_data)} questions...") for item in questions_data: task_id = item.get("task_id") question_text = item.get("question") if not task_id or question_text is None: print(f"Skipping item with missing task_id or question: {item}") continue try: submitted_answer = agent(question_text) answers_payload.append( {"task_id": task_id, "submitted_answer": submitted_answer} ) results_log.append( { "Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer, } ) except Exception as e: print(f"Error running agent on task {task_id}: {e}") results_log.append( { "Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}", } ) if not answers_payload: print("Agent did not produce any answers to submit.") return "Agent did not produce any answers to submit.", pd.DataFrame(results_log) # 4. Prepare Submission submission_data = { "username": username.strip(), "agent_code": agent_code, "answers": answers_payload, } status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..." print(status_update) # 5. Submit print(f"Submitting {len(answers_payload)} answers to: {submit_url}") try: response = requests.post(submit_url, json=submission_data, timeout=60) response.raise_for_status() result_data = response.json() final_status = ( f"Submission Successful!\n" f"User: {result_data.get('username')}\n" f"Overall Score: {result_data.get('score', 'N/A')}% " f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n" f"Message: {result_data.get('message', 'No message received.')}" ) print("Submission successful.") results_df = pd.DataFrame(results_log) return final_status, results_df except requests.exceptions.HTTPError as e: error_detail = f"Server responded with status {e.response.status_code}." try: error_json = e.response.json() error_detail += f" Detail: {error_json.get('detail', e.response.text)}" except requests.exceptions.JSONDecodeError: error_detail += f" Response: {e.response.text[:500]}" status_message = f"Submission Failed: {error_detail}" print(status_message) results_df = pd.DataFrame(results_log) return status_message, results_df except requests.exceptions.Timeout: status_message = "Submission Failed: The request timed out." print(status_message) results_df = pd.DataFrame(results_log) return status_message, results_df except requests.exceptions.RequestException as e: status_message = f"Submission Failed: Network error - {e}" print(status_message) results_df = pd.DataFrame(results_log) return status_message, results_df except Exception as e: status_message = f"An unexpected error occurred during submission: {e}" print(status_message) results_df = pd.DataFrame(results_log) return status_message, results_df # --- Build Gradio Interface using Blocks --- with gr.Blocks() as demo: gr.Markdown("# Basic Agent Evaluation Runner") gr.Markdown( """ **Instructions:** 1. Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ... 2. Log in to your Hugging Face account using the button below. This uses your HF username for submission. 3. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score. --- **Disclaimers:** Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions). This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async. """ ) gr.LoginButton() run_button = gr.Button("Run Evaluation & Submit All Answers") status_output = gr.Textbox( label="Run Status / Submission Result", lines=5, interactive=False ) # Removed max_rows=10 from DataFrame constructor results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True) run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table]) if __name__ == "__main__": print("\n" + "-" * 30 + " App Starting " + "-" * 30) # Check for SPACE_HOST and SPACE_ID at startup for information space_host_startup = os.getenv("SPACE_HOST") space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup if space_host_startup: print(f"✅ SPACE_HOST found: {space_host_startup}") print(f" Runtime URL should be: https://{space_host_startup}.hf.space") else: print("ℹ️ SPACE_HOST environment variable not found (running locally?).") if space_id_startup: # Print repo URLs if SPACE_ID is found print(f"✅ SPACE_ID found: {space_id_startup}") print(f" Repo URL: https://huggingface.co/spaces/{space_id_startup}") print( f" Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main" ) else: print( "ℹ️ SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined." ) print("-" * (60 + len(" App Starting ")) + "\n") print("Launching Gradio Interface for Basic Agent Evaluation...") demo.launch(debug=True, share=False)